knitr::include_graphics("assets/nt2.png", dpi=00)
masthead <- "assets/nt2.png"
df<-read.csv('hw/drug overdoses.csv')#(World Data For Death Caused By Drug Over Dose)
df_1<-df
df_1$Deaths.Opioid<-format(round(df_1$Deaths.Opioid,0), nsmall=0)
df_1$Deaths.Cocaine<-format(round(df_1$Deaths.Cocaine,0), nsmall=0)
df_1$Deaths.other.drug<-format(round(df_1$Deaths.other.drug,0), nsmall=0)
df_1$Deaths.Amphetamine<-format(round(df_1$Deaths.Amphetamine,0), nsmall=0)
df_1
df_2<-df
df_2<-df_2%>%select(Entity,Deaths.Opioid,Deaths.Cocaine,Deaths.other.drug,Deaths.Amphetamine)%>%rename(Country='Entity')
df_2<-df_2%>%arrange(Country)%>%filter((Country=="Mauritius") | (Country=="Uganda") | (Country=="Rwanda")| (Country=="Kenya")| (Country=="Ethiopia")| (Country=="Tanzania")| (Country=="Eritrea")| (Country=="Madagascar")| (Country=="Somalia")| (Country=="Djibouti"))
#%>%select(Country,`Deaths.Opioid`, `Deaths.Cocaine`,`Deaths.other.drug`,`Deaths.Amphetamine`)
df_11<-df_2
df_11$Deaths.Opioid<-format(round(df_11$Deaths.Opioid,0), nsmall=0)
df_11$Deaths.Cocaine<-format(round(df_11$Deaths.Cocaine,0), nsmall=0)
df_11$Deaths.other.drug<-format(round(df_11$Deaths.other.drug,0), nsmall=0)
df_11$Deaths.Amphetamine<-format(round(df_11$Deaths.Amphetamine,0), nsmall=0)
df_11
missing_stats <- purrr::map_df(df_2, ~ sum(is.na(.))) %>%
gather('Column name', 'Count of missing values')
missing_stats
df_scaled<-df_2
df_scaled[,2:5] <- scale(df_2[,2:5])
df_scaled
# enter your code here
if(!require(devtools)) install.packages("devtools")
#devtools::install_github("kassambara/factoextra")
library(factoextra)
### Elbow method (look at the knee)
v1<-fviz_nbclust(df_scaled[,2:5], kmeans, method = "wss") +
geom_vline(xintercept = 3, linetype = 2)
girafe(ggobj = v1, width_svg = 13, height_svg = 7,
options = list(opts_sizing(rescale = TRUE, width = 1.0)))
df_2<-df
df_2<-df_2%>%select(Entity,Deaths.Opioid,Deaths.Cocaine,Deaths.other.drug,Deaths.Amphetamine)%>%rename(Country='Entity')
df_2<-df_2%>%arrange(Country)%>%filter((Country=="Mauritius") | (Country=="Uganda") | (Country=="Rwanda")| (Country=="Kenya")| (Country=="Ethiopia")| (Country=="Tanzania")| (Country=="Eritrea")| (Country=="Madagascar")| (Country=="Somalia")| (Country=="Djibouti"))
#%>%select(Country,`Deaths.Opioid`, `Deaths.Cocaine`,`Deaths.other.drug`,`Deaths.Amphetamine`)
df_2 <- df_2 %>%
group_by(`Country`,) %>%
summarise(Deaths.Opioid=sum(`Deaths.Opioid`),Deaths.Cocaine = sum(`Deaths.Cocaine`),Deaths.other.drug = sum(`Deaths.other.drug`),Deaths.Amphetamine=sum(`Deaths.Amphetamine`))
df_scaled<-df_2
df_scaled[,2:5] <- scale(df_2[,2:5])
df_scaled
library(stats)
set.seed(123)
clusters <- kmeans(df_scaled[,2:5], 3, iter.max = 20, nstart = 25)
df_2$cluster <- as.factor(clusters$cluster)
df_2
# enter your code here
v2 <- fviz_cluster(clusters, geom="point", data=df_2[,2:5],palette = "Set2") +
ggtitle("K=3") +
theme_minimal()
girafe(ggobj = v2, width_svg = 13, height_svg = 7,
options = list(opts_sizing(rescale = TRUE, width = 1.0)))
mean_data <-df_2 %>%
group_by(cluster)%>%
summarise(n = n(),
Deaths.Opioid = mean(Deaths.Opioid),
Deaths.Cocaine = mean(Deaths.Cocaine),
Deaths.other.drug = mean(Deaths.other.drug),
Deaths.Amphetamine = mean( Deaths.Amphetamine))
mean_data
df_group3<-df_2%>%filter(cluster==1)
df_group3
df_3<-df
df_3<-df_3%>%arrange(Year)%>%rename(Country='Entity')
df_3<-df_3%>%arrange(Country)%>% filter((Country=="Mauritius") | (Country=="Uganda") | (Country=="Rwanda")| (Country=="Kenya")| (Country=="Ethiopia")| (Country=="Tanzania")| (Country=="Eritrea")| (Country=="Madagascar")| (Country=="Somalia")| (Country=="Djibouti"))
df_3 <- df_3 %>%
group_by(`Country`,`Year`) %>%
summarise(Deaths.Opioid=sum(`Deaths.Opioid`),Deaths.Cocaine = sum(`Deaths.Cocaine`),Deaths.other.drug = sum(`Deaths.other.drug`),Deaths.Amphetamine=sum(`Deaths.Amphetamine`))
#%>%select(Country,`Deaths.Opioid`, `Deaths.Cocaine`,`Deaths.other.drug`,`Deaths.Amphetamine`)
df_33 <- df_3 %>%
group_by(`Country`) %>%
summarise(Deaths.Opioid=sum(`Deaths.Opioid`),Deaths.Cocaine = sum(`Deaths.Cocaine`),Deaths.other.drug = sum(`Deaths.other.drug`),Deaths.Amphetamine=sum(`Deaths.Amphetamine`))
df_5<-df_33
df_5$Deaths.Opioid<-format(round(df_5$Deaths.Opioid,0), nsmall=0)
df_5$Deaths.Cocaine<-format(round(df_5$Deaths.Cocaine,0), nsmall=0)
df_5$Deaths.other.drug<-format(round(df_5$Deaths.other.drug,0), nsmall=0)
df_5$Deaths.Amphetamine<-format(round(df_5$Deaths.Amphetamine,0), nsmall=0)
df_5
library(treemapify)
library(ggiraph)
v2 <- ggplot(df_33, aes(area = Deaths.Opioid, fill = Deaths.Opioid, label = Country)) +ggtitle("Deaths caused by Opioid") +
geom_treemap() +
geom_treemap_text(fontface = "italic", colour = "white", place = "centre",
grow = TRUE)
girafe(ggobj = v2, width_svg = 16, height_svg = 10,
options = list(
opts_sizing(rescale = TRUE, width = 0.8) )
)
theme_opts <- theme(
plot.margin = margin(.25, 1, .25, .25, "cm"),
plot.background = element_blank(),
panel.background = element_blank(),
legend.position = "none",
axis.title.x=element_blank(),
axis.title.y=element_blank(),
axis.ticks.y=element_blank(),
axis.ticks.x=element_blank(),
axis.text.x=element_blank(),
strip.placement = "outside", # Place facet labels outside x axis labels.
strip.background = element_rect(fill = "white"), # Make facet label background white.
axis.title = element_blank() # Remove x and y axis titles.
)
# Make the plot
v1 <- ggplot(df_3, aes(x=Deaths.Cocaine, y=Country)) +
geom_bar(stat="identity", fill="#88b88a") +
geom_text( data = df_33, size = 4, label = df_5$Deaths.Cocaine, hjust = 0, position = position_nudge(x = 12), color = 'gray30') +
# scale_y_discrete(limits=c("Almond milk", "Oat milk", "Soy milk", "Rice milk","Cow's milk")) +
#scale_fill_manual(values=c("Carbon Emissions (kg CO2eq)" = "#364e5d", "Land Use (m2)" = "#597e4e", "Water Use (L)" = "#587f89")) +
#scale_color_manual(values=c("white" = "#ffffff", "black" = "#000000")) +
coord_cartesian(clip="off") +
labs(title = "total Death caused by cocaine in East Africa") +
theme_opts
# Print the plot
v1
theme_opts <- theme(
plot.margin = margin(.25, 1, .25, .25, "cm"),
plot.background = element_blank(),
panel.background = element_blank(),
legend.position = "none",
axis.title.x=element_blank(),
axis.title.y=element_blank(),
axis.ticks.y=element_blank(),
axis.ticks.x=element_blank(),
axis.text.x=element_blank(),
strip.placement = "outside", # Place facet labels outside x axis labels.
strip.background = element_rect(fill = "white"), # Make facet label background white.
axis.title = element_blank() # Remove x and y axis titles.
)
# Make the plot
v1 <- ggplot(df_3, aes(x=Deaths.Amphetamine, y=Country)) +
geom_bar(stat="identity", fill="#0000FF") +
geom_text( data = df_33, size = 4, label = df_5$Deaths.Amphetamine, hjust = 0, position = position_nudge(x = 12), color = 'blue') +
# scale_y_discrete(limits=c("Almond milk", "Oat milk", "Soy milk", "Rice milk","Cow's milk")) +
#scale_fill_manual(values=c("Carbon Emissions (kg CO2eq)" = "#364e5d", "Land Use (m2)" = "#597e4e", "Water Use (L)" = "#587f89")) +
#scale_color_manual(values=c("white" = "#ffffff", "black" = "#000000")) +
coord_cartesian(clip="off") +
labs(title = "total Death caused by Amphetaminecocaine in East Africa") +
theme_opts
# Print the plot
v1
theme_opts <- theme(
plot.margin = margin(.25, 1, .25, .25, "cm"),
plot.background = element_blank(),
panel.background = element_blank(),
legend.position = "none",
axis.title.x=element_blank(),
axis.title.y=element_blank(),
axis.ticks.y=element_blank(),
axis.ticks.x=element_blank(),
axis.text.x=element_blank(),
strip.placement = "outside", # Place facet labels outside x axis labels.
strip.background = element_rect(fill = "white"), # Make facet label background white.
axis.title = element_blank() # Remove x and y axis titles.
)
# Make the plot
v1 <- ggplot(df_3, aes(x=Deaths.other.drug, y=Country)) +
geom_bar(stat="identity", fill="#FFFF00") +
geom_text( data = df_33, size = 4, label = df_5$Deaths.other.drug, hjust = 0, position = position_nudge(x = 12), color = 'yellow') +
# scale_y_discrete(limits=c("Almond milk", "Oat milk", "Soy milk", "Rice milk","Cow's milk")) +
#scale_fill_manual(values=c("Carbon Emissions (kg CO2eq)" = "#364e5d", "Land Use (m2)" = "#597e4e", "Water Use (L)" = "#587f89")) +
#scale_color_manual(values=c("white" = "#ffffff", "black" = "#000000")) +
coord_cartesian(clip="off") +
labs(title = "total Death caused by other Drugs in East Africa") +
theme_opts
# Print the plot
v1
knitr::include_graphics("assets/drug-OD1.Jpg", dpi=00)
masthead <- "assets/drug-OD1.Jpg"
Drugs take you to hell, disguised as heaven.
— Donald Lyn
mean_data <-df_2 %>%
group_by(cluster)%>%
summarise(n = n(),
Deaths.Opioid = mean(Deaths.Opioid),
Deaths.Cocaine = mean(Deaths.Cocaine),
Deaths.other.drug = mean(Deaths.other.drug),
Deaths.Amphetamine = mean( Deaths.Amphetamine))
mean_data
Heroin is an opioid drug made from morphine, a natural substance taken from the seed pod of the various opium poppy plants grown in Southeast.
— National Institute on Drug Abuse
df_deaths <- df_33 %>% select(Country, Deaths.Opioid)
#remove effects where deaths is NA
df_deaths <- df_deaths[!is.na(df_deaths$Deaths.Opioid), ]
# creating a percentage column
df_deaths <- mutate(df_deaths, Percent=round(100*df_deaths$Deaths.Opioid/sum(df_deaths$Deaths.Opioid)))
df_deaths <- df_deaths %>% filter(df_deaths$Percent > 2)
#df_deaths
df_deathsx<-df_deaths
df_deathsx$Deaths.Opioid<-format(round(df_deathsx$Deaths.Opioid), nsmall=0)
df_deathsx
theme_opts <- theme_minimal() + theme(
panel.grid.major.x = element_blank(),
panel.grid.major.y = element_blank(),
panel.grid.minor.x = element_blank(),
panel.grid.minor.y = element_blank(),
axis.ticks = element_line(),
panel.background = element_rect(fill = "white", colour = "white"),
legend.position = "right"
)
area <- ggplot(df_deaths, aes(x="", y= Deaths.Opioid, fill= Country)) +
geom_col(color="black")+
geom_text_repel(aes(label = paste(df_deathsx$Deaths.Opioid,"-",df_deaths$Percent,"%")),
color = "white",
position = position_stack(vjust = 0.5),
show.legend = FALSE) +
coord_polar(theta = "y")+
labs(title = "Number of Deaths per Opioid death", subtitle = "Preliminary Analysis") +
theme_minimal() +
theme_opts
area
ggsave(filename = "assets/ethiopia-disaster-deaths.svg", plot = area, width=13, height=4)
df_7<-df
df_7<-df_7%>%arrange(Year)%>%rename(Country='Entity')
df_7<-df_7%>%arrange(Country)%>% filter( (Country=="Ethiopia"))
df_7$Deaths.Opioid<-format(round(df_7$Deaths.Opioid), nsmall=0)
#Wrangling data
df_7 <- df_7 %>% select(Year,Deaths.Opioid)
df_8<-df_7
df_8 <- transform(df_7,Deaths.Opioid = as.numeric(Deaths.Opioid))
df_8
#fit simple linear regression model
#model <- lm(df_temp$Deaths~df_temp$Year)
#view model summary
#summary(model)
#Call:
#lm(formula = df_temp$Deaths~df_temp$Year)
#From the model we see, Deaths=(-6325.840) + 3.303*(f_temp$Year)
theme_opts <- theme(
plot.title = element_text(color = "black", size = 12, face = "bold"),
plot.subtitle = element_text(color = "black", size = 8),
plot.caption = element_text(color = "#555555", size = 8),
axis.title.x = element_blank(),
axis.title.y = element_blank(),
# axis.text.x = element_text(vjust = 12),
panel.border = element_blank(),
panel.background = element_blank(),
panel.grid.minor = element_blank(), # remove minor gridlines
panel.grid.major.x = element_blank(), # remove x (vertical) gridlines
legend.title = element_blank(), # remove legend title
legend.text = element_text(color = "black", size = 8),
legend.position='top'
)
# Plot
v1 <- ggplot(df_8, aes(x=Year, y=Deaths.Opioid)) +
geom_line(aes(y=Deaths.Opioid), color="blue") +
geom_area(color = "#458cb6", fill= "#a1b5d2", alpha=1.0 , size=0.5) +
#geom_hline(yintercept = c(seq(0, 100, 10)), color="#ffffff", size=0.25, alpha=0.2) + # gridlines in the forefront
scale_x_continuous(breaks=c(1990,1993,1996,1999,2002,2005,2007,2010,2013,2016,2019)) +
scale_y_continuous(breaks=seq(0, 300, 10)) +
labs( title = "opioid data for Ethiopia!",
subtitle = "total death of opioid from 1990 to 2017") +
theme_bw() +
annotate("text", x = 1997, y = 110,
label = paste0("In 1997 - the highest peak", "\n", "Deaths Number = 110"),
hjust = "left", vjust = 0, color = "#000000", size = 4, fontface = 1) +
annotate("text", x = 2016, y = 97,
label = paste0(" 2017 peak", "\n", "Deaths=97"),
hjust = "left", vjust = 0, color = "#000000", size = 4, fontface = 1) +
theme_opts
v1
df_22<-df
df_22<-df_22%>%select(Entity,Year,Deaths.Opioid)%>%rename(Country='Entity')
df_22<-df_22%>%arrange(Country)%>%filter( (Country=="Ethiopia"))
#%>%select(Country,`Deaths.Opioid`, `Deaths.Cocaine`,`Deaths.other.drug`,`Deaths.Amphetamine`)
df_22 <- df_22 %>%
group_by(`Year`,) %>%
summarise(Deaths.Opioid=sum(`Deaths.Opioid`))
mean_data1 <-df_22%>%
rename(Deaths.Opioid.mean='Deaths.Opioid') %>%
group_by(Year)%>%
summarise(
Deaths.Opioid.mean = mean(Deaths.Opioid.mean))
mean_data1
df_23 <-mean_data1 %>%
select(date=Year,Deaths.Opioid.mean)%>%
arrange(date)
df_23$date <- as.Date(mean_data1$Year,"1901-01-01")
df_23
library(TTR)
df_24 <- df_23%>%mutate(MA=ALMA(Deaths.Opioid.mean, n = 9, offset = 0.85, sigma = 6))
df_24
ggplot(data=df_24, aes(x=date)) +
geom_line(mapping=aes(y=MA, color="MA"),group = 1,size=1)+
geom_line(mapping=aes(y=Deaths.Opioid.mean, color="mean_Deaths.Opioid"),group = 1,size=1)+
theme(panel.grid = element_blank(),
axis.ticks = element_blank(),
strip.background = element_blank(),
panel.background = element_blank(),
axis.title.x=element_blank(),
axis.title.y=element_blank()) +
scale_color_manual(values = c(Deaths.Opioid.mean="black",
MA="red"))
# References ## The citations and data sources used for this case